Related papers: SWIFT: Using task-based parallelism, fully asynchr…

We provide a framework for the design and analysis of dynamic programming algorithms for surface-embedded graphs on n vertices and branchwidth at most k. Our technique applies to general families of problems where standard dynamic…

We present Swallow, a scalable many-core architecture, with a current configuration of 480 x 32-bit processors. Swallow is an open-source architecture, designed from the ground up to deliver scalable increases in usable computational power…

Networking is considered a datacenter tax, and hyperscalers push hard to provide high-performance networking with minimal resource expenditure. To keep up with the ever-increasing network rates, many CPU cycles are spent on the networking…

Modern graphics processing units (GPUs) lead to a major increase in the performance of the computation of astrophysical simulations. Owing to the different nature of GPU architecture compared to traditional central processing units (CPUs)…

Split computing ($\neq$ split learning) is a promising approach to deep learning models for resource-constrained edge computing systems, where weak sensor (mobile) devices are wirelessly connected to stronger edge servers through channels…

The fundamental success of large language models hinges upon the efficacious implementation of large-scale distributed training techniques. Nevertheless, building a vast, high-performance cluster featuring high-speed communication…

Summarising distributed data is a central routine for parallel programming, lying at the core of widely used frameworks such as the map/reduce paradigm. In the IoT context it is even more crucial, being a privileged mean to allow long-range…

We discuss the design and implementation of HYDRA_OMP a parallel implementation of the Smoothed Particle Hydrodynamics-Adaptive P3M (SPH-AP3M) code HYDRA. The code is designed primarily for conducting cosmological hydrodynamic simulations…

Large language models (LLMs) have achieved remarkable success in natural language tasks, but their inference incurs substantial computational and memory overhead. To improve efficiency, parallel decoding methods like Skeleton-of-Thought…

Although modern, AI-centric datacenters heavily rely on SmartNICs, existing devices impose a hard trade-off. Commercial SmartNICs provide high bandwidth and easy software integration, but offer limited support for customization and data…

Graph Convolutional Networks (GCNs) are extensively utilized for deep learning on graphs. The large data sizes of graphs and their vertex features make scalable training algorithms and distributed memory systems necessary. Since the…

Graph partitioning plays a vital role in distributedlarge-scale web graph analytics, such as pagerank and labelpropagation. The quality and scalability of partitioning strategyhave a strong impact on such communication- and…

Attention mechanisms have become a core component of deep learning models, with Channel Attention and Spatial Attention being the two most representative architectures. Current research on their fusion strategies primarily bifurcates into…

Recently, graph mining approaches have become very popular, especially in domains such as bioinformatics, chemoinformatics and social networks. In this scope, one of the most challenging tasks is frequent subgraph discovery. This task has…

Recent development in Large Language Models (LLMs) and Multi-modal Large Language Models (MLLMs) have leverage Attention-based Transformer architectures and achieved superior performance and generalization capabilities. They have since…

Transfer learning can be seen as a data- and compute-efficient alternative to training models from scratch. The emergence of rich model repositories, such as TensorFlow Hub, enables practitioners and researchers to unleash the potential of…

The conventional approach to scaling Software Defined Networking (SDN) controllers today is to partition switches based on network topology, with each partition being controlled by a single physical controller, running all SDN applications.…

Graph partitioning schedules parallel calculations like sparse matrix-vector multiply (SpMV). We consider contiguous partitions, where the $m$ rows (or columns) of a sparse matrix with $N$ nonzeros are split into $K$ parts without…

To enable the pre-trained models to be fine-tuned with local data on edge devices without sharing data with the cloud, we design an efficient split fine-tuning (SFT) framework for edge and cloud collaborative learning. We propose three…

Graph search and sparse data-structure traversal workloads contain challenging irregular memory patterns on global data structures that need to be modified atomically. Distributed processing of these workloads has relied on server threads…